Online learning of windmill time series using Long Short-term Cognitive Networks
Autor: | Alejandro Morales-Hernández, Gonzalo Nápoles, Agnieszka Jastrzebska, Yamisleydi Salgueiro, Koen Vanhoof |
---|---|
Přispěvatelé: | Cognitive Science & AI, MORALES HERNANDEZ, Alejandro, Salgueiro, Yamisleydi, NAPOLES RUIZ, Gonzalo, VANHOOF, Koen, Jastrzebska, Agnieszka |
Rok vydání: | 2021 |
Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning Neural-network Energy Time Series Forecasting Computer Science - Artificial Intelligence Recurrent Neural Network General Engineering Integration Computer Science Applications Machine Learning (cs.LG) Artificial Intelligence (cs.AI) Artificial Intelligence Long Short-term Cognitive Network Challenges Multivariate time series Hidden Markov-Models Forecasting |
Zdroj: | Expert Systems with Applications, 205:117721, 1-9. Elsevier Limited Joint International Scientific Conferences on AI and Machine Learning BNAIC/BeNeLearn 2022 Tilburg University-PURE |
ISSN: | 0957-4174 |
DOI: | 10.48550/arxiv.2107.00425 |
Popis: | Forecasting windmill time series is often the basis of other processes such as anomaly detection, health monitoring, or maintenance scheduling. The amount of data generated by windmill farms makes online learning the most viable strategy to follow. Such settings require retraining the model each time a new batch of data is available. However, updating the model with new information is often very expensive when using traditional Recurrent Neural Networks (RNNs). In this paper, we use Long Short-term Cognitive Networks (LSTCNs) to forecast windmill time series in online settings. These recently introduced neural systems consist of chained Short-term Cognitive Network blocks, each processing a temporal data chunk. The learning algorithm of these blocks is based on a very fast, deterministic learning rule that makes LSTCNs suitable for online learning tasks. The numerical simulations using a case study involving four windmills showed that our approach reported the lowest forecasting errors with respect to a simple RNN, a Long Short-term Memory, a Gated Recurrent Unit, and a Hidden Markov Model. What is perhaps more important is that the LSTCN approach is significantly faster than these state-of-the-art models. |
Databáze: | OpenAIRE |
Externí odkaz: |